Pushing the docs to dev/ for branch: master, commit c1f58745be7c4923cf0a666f1c6bf052042f131e

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -15,7 +15,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# L1 Penalty and Sparsity in Logistic Regression\n\n\nComparison of the sparsity (percentage of zero coefficients) of solutions when\nL1 and L2 penalty are used for different values of C. We can see that large\nvalues of C give more freedom to the model.  Conversely, smaller values of C\nconstrain the model more. In the L1 penalty case, this leads to sparser\nsolutions.\n\nWe classify 8x8 images of digits into two classes: 0-4 against 5-9.\nThe visualization shows coefficients of the models for varying C.\n\n"
+        "\n# L1 Penalty and Sparsity in Logistic Regression\n\n\nComparison of the sparsity (percentage of zero coefficients) of solutions when\nL1, L2 and Elastic-Net penalty are used for different values of C. We can see\nthat large values of C give more freedom to the model.  Conversely, smaller\nvalues of C constrain the model more. In the L1 penalty case, this leads to\nsparser solutions. As expected, the Elastic-Net penalty sparsity is between\nthat of L1 and L2.\n\nWe classify 8x8 images of digits into two classes: 0-4 against 5-9.\nThe visualization shows coefficients of the models for varying C.\n\n"
       ]
     },
     {
@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Authors: Alexandre Gramfort <[email protected]>\n#          Mathieu Blondel <[email protected]>\n#          Andreas Mueller <[email protected]>\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn import datasets\nfrom sklearn.preprocessing import StandardScaler\n\ndigits = datasets.load_digits()\n\nX, y = digits.data, digits.target\nX = StandardScaler().fit_transform(X)\n\n# classify small against large digits\ny = (y > 4).astype(np.int)\n\n\n# Set regularization parameter\nfor i, C in enumerate((1, 0.1, 0.01)):\n    # turn down tolerance for short training time\n    clf_l1_LR = LogisticRegression(C=C, penalty='l1', tol=0.01, solver='saga')\n    clf_l2_LR = LogisticRegression(C=C, penalty='l2', tol=0.01, solver='saga')\n    clf_l1_LR.fit(X, y)\n    clf_l2_LR.fit(X, y)\n\n    coef_l1_LR = clf_l1_LR.coef_.ravel()\n    coef_l2_LR = clf_l2_LR.coef_.ravel()\n\n    # coef_l1_LR contains zeros due to the\n    # L1 sparsity inducing norm\n\n    sparsity_l1_LR = np.mean(coef_l1_LR == 0) * 100\n    sparsity_l2_LR = np.mean(coef_l2_LR == 0) * 100\n\n    print(\"C=%.2f\" % C)\n    print(\"Sparsity with L1 penalty: %.2f%%\" % sparsity_l1_LR)\n    print(\"score with L1 penalty: %.4f\" % clf_l1_LR.score(X, y))\n    print(\"Sparsity with L2 penalty: %.2f%%\" % sparsity_l2_LR)\n    print(\"score with L2 penalty: %.4f\" % clf_l2_LR.score(X, y))\n\n    l1_plot = plt.subplot(3, 2, 2 * i + 1)\n    l2_plot = plt.subplot(3, 2, 2 * (i + 1))\n    if i == 0:\n        l1_plot.set_title(\"L1 penalty\")\n        l2_plot.set_title(\"L2 penalty\")\n\n    l1_plot.imshow(np.abs(coef_l1_LR.reshape(8, 8)), interpolation='nearest',\n                   cmap='binary', vmax=1, vmin=0)\n    l2_plot.imshow(np.abs(coef_l2_LR.reshape(8, 8)), interpolation='nearest',\n                   cmap='binary', vmax=1, vmin=0)\n    plt.text(-8, 3, \"C = %.2f\" % C)\n\n    l1_plot.set_xticks(())\n    l1_plot.set_yticks(())\n    l2_plot.set_xticks(())\n    l2_plot.set_yticks(())\n\nplt.show()"
+        "print(__doc__)\n\n# Authors: Alexandre Gramfort <[email protected]>\n#          Mathieu Blondel <[email protected]>\n#          Andreas Mueller <[email protected]>\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn import datasets\nfrom sklearn.preprocessing import StandardScaler\n\ndigits = datasets.load_digits()\n\nX, y = digits.data, digits.target\nX = StandardScaler().fit_transform(X)\n\n# classify small against large digits\ny = (y > 4).astype(np.int)\n\nl1_ratio = 0.5  # L1 weight in the Elastic-Net regularization\n\nfig, axes = plt.subplots(3, 3)\n\n# Set regularization parameter\nfor i, (C, axes_row) in enumerate(zip((1, 0.1, 0.01), axes)):\n    # turn down tolerance for short training time\n    clf_l1_LR = LogisticRegression(C=C, penalty='l1', tol=0.01, solver='saga')\n    clf_l2_LR = LogisticRegression(C=C, penalty='l2', tol=0.01, solver='saga')\n    clf_en_LR = LogisticRegression(C=C, penalty='elasticnet', solver='saga',\n                                   l1_ratio=l1_ratio, tol=0.01)\n    clf_l1_LR.fit(X, y)\n    clf_l2_LR.fit(X, y)\n    clf_en_LR.fit(X, y)\n\n    coef_l1_LR = clf_l1_LR.coef_.ravel()\n    coef_l2_LR = clf_l2_LR.coef_.ravel()\n    coef_en_LR = clf_en_LR.coef_.ravel()\n\n    # coef_l1_LR contains zeros due to the\n    # L1 sparsity inducing norm\n\n    sparsity_l1_LR = np.mean(coef_l1_LR == 0) * 100\n    sparsity_l2_LR = np.mean(coef_l2_LR == 0) * 100\n    sparsity_en_LR = np.mean(coef_en_LR == 0) * 100\n\n    print(\"C=%.2f\" % C)\n    print(\"{:<40} {:.2f}%\".format(\"Sparsity with L1 penalty:\", sparsity_l1_LR))\n    print(\"{:<40} {:.2f}%\".format(\"Sparsity with Elastic-Net penalty:\",\n                                  sparsity_en_LR))\n    print(\"{:<40} {:.2f}%\".format(\"Sparsity with L2 penalty:\", sparsity_l2_LR))\n    print(\"{:<40} {:.2f}\".format(\"Score with L1 penalty:\",\n                                 clf_l1_LR.score(X, y)))\n    print(\"{:<40} {:.2f}\".format(\"Score with Elastic-Net penalty:\",\n                                 clf_en_LR.score(X, y)))\n    print(\"{:<40} {:.2f}\".format(\"Score with L2 penalty:\",\n                                 clf_l2_LR.score(X, y)))\n\n    if i == 0:\n        axes_row[0].set_title(\"L1 penalty\")\n        axes_row[1].set_title(\"Elastic-Net\\nl1_ratio = %s\" % l1_ratio)\n        axes_row[2].set_title(\"L2 penalty\")\n\n    for ax, coefs in zip(axes_row, [coef_l1_LR, coef_en_LR, coef_l2_LR]):\n        ax.imshow(np.abs(coefs.reshape(8, 8)), interpolation='nearest',\n                  cmap='binary', vmax=1, vmin=0)\n        ax.set_xticks(())\n        ax.set_yticks(())\n\n    axes_row[0].set_ylabel('C = %s' % C)\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -4,10 +4,11 @@
 ==============================================
 
 Comparison of the sparsity (percentage of zero coefficients) of solutions when
-L1 and L2 penalty are used for different values of C. We can see that large
-values of C give more freedom to the model.  Conversely, smaller values of C
-constrain the model more. In the L1 penalty case, this leads to sparser
-solutions.
+L1, L2 and Elastic-Net penalty are used for different values of C. We can see
+that large values of C give more freedom to the model.  Conversely, smaller
+values of C constrain the model more. In the L1 penalty case, this leads to
+sparser solutions. As expected, the Elastic-Net penalty sparsity is between
+that of L1 and L2.
 
 We classify 8x8 images of digits into two classes: 0-4 against 5-9.
 The visualization shows coefficients of the models for varying C.
@@ -35,45 +36,55 @@
 # classify small against large digits
 y = (y > 4).astype(np.int)
 
+l1_ratio = 0.5  # L1 weight in the Elastic-Net regularization
+
+fig, axes = plt.subplots(3, 3)
 
 # Set regularization parameter
-for i, C in enumerate((1, 0.1, 0.01)):
+for i, (C, axes_row) in enumerate(zip((1, 0.1, 0.01), axes)):
     # turn down tolerance for short training time
     clf_l1_LR = LogisticRegression(C=C, penalty='l1', tol=0.01, solver='saga')
     clf_l2_LR = LogisticRegression(C=C, penalty='l2', tol=0.01, solver='saga')
+    clf_en_LR = LogisticRegression(C=C, penalty='elasticnet', solver='saga',
+                                   l1_ratio=l1_ratio, tol=0.01)
     clf_l1_LR.fit(X, y)
     clf_l2_LR.fit(X, y)
+    clf_en_LR.fit(X, y)
 
     coef_l1_LR = clf_l1_LR.coef_.ravel()
     coef_l2_LR = clf_l2_LR.coef_.ravel()
+    coef_en_LR = clf_en_LR.coef_.ravel()
 
     # coef_l1_LR contains zeros due to the
     # L1 sparsity inducing norm
 
     sparsity_l1_LR = np.mean(coef_l1_LR == 0) * 100
     sparsity_l2_LR = np.mean(coef_l2_LR == 0) * 100
+    sparsity_en_LR = np.mean(coef_en_LR == 0) * 100
 
     print("C=%.2f" % C)
-    print("Sparsity with L1 penalty: %.2f%%" % sparsity_l1_LR)
-    print("score with L1 penalty: %.4f" % clf_l1_LR.score(X, y))
-    print("Sparsity with L2 penalty: %.2f%%" % sparsity_l2_LR)
-    print("score with L2 penalty: %.4f" % clf_l2_LR.score(X, y))
+    print("{:<40} {:.2f}%".format("Sparsity with L1 penalty:", sparsity_l1_LR))
+    print("{:<40} {:.2f}%".format("Sparsity with Elastic-Net penalty:",
+                                  sparsity_en_LR))
+    print("{:<40} {:.2f}%".format("Sparsity with L2 penalty:", sparsity_l2_LR))
+    print("{:<40} {:.2f}".format("Score with L1 penalty:",
+                                 clf_l1_LR.score(X, y)))
+    print("{:<40} {:.2f}".format("Score with Elastic-Net penalty:",
+                                 clf_en_LR.score(X, y)))
+    print("{:<40} {:.2f}".format("Score with L2 penalty:",
+                                 clf_l2_LR.score(X, y)))
 
-    l1_plot = plt.subplot(3, 2, 2 * i + 1)
-    l2_plot = plt.subplot(3, 2, 2 * (i + 1))
     if i == 0:
-        l1_plot.set_title("L1 penalty")
-        l2_plot.set_title("L2 penalty")
-
-    l1_plot.imshow(np.abs(coef_l1_LR.reshape(8, 8)), interpolation='nearest',
-                   cmap='binary', vmax=1, vmin=0)
-    l2_plot.imshow(np.abs(coef_l2_LR.reshape(8, 8)), interpolation='nearest',
-                   cmap='binary', vmax=1, vmin=0)
-    plt.text(-8, 3, "C = %.2f" % C)
-
-    l1_plot.set_xticks(())
-    l1_plot.set_yticks(())
-    l2_plot.set_xticks(())
-    l2_plot.set_yticks(())
+        axes_row[0].set_title("L1 penalty")
+        axes_row[1].set_title("Elastic-Net\nl1_ratio = %s" % l1_ratio)
+        axes_row[2].set_title("L2 penalty")
+
+    for ax, coefs in zip(axes_row, [coef_l1_LR, coef_en_LR, coef_l2_LR]):
+        ax.imshow(np.abs(coefs.reshape(8, 8)), interpolation='nearest',
+                  cmap='binary', vmax=1, vmin=0)
+        ax.set_xticks(())
+        ax.set_yticks(())
+
+    axes_row[0].set_ylabel('C = %s' % C)
 
 plt.show()